Cargando…

Breast Mass Classification Using Diverse Contextual Information and Convolutional Neural Network

Masses are one of the early signs of breast cancer, and the survival rate of women suffering from breast cancer can be improved if masses can be correctly identified as benign or malignant. However, their classification is challenging due to the similarity in texture patterns of both types of mass....

Descripción completa

Detalles Bibliográficos
Autores principales: Busaleh, Mariam, Hussain, Muhammad, Aboalsamh, Hatim A., Amin, Fazal-e-
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8615673/
https://www.ncbi.nlm.nih.gov/pubmed/34821634
http://dx.doi.org/10.3390/bios11110419
_version_ 1784604161399062528
author Busaleh, Mariam
Hussain, Muhammad
Aboalsamh, Hatim A.
Amin, Fazal-e-
author_facet Busaleh, Mariam
Hussain, Muhammad
Aboalsamh, Hatim A.
Amin, Fazal-e-
author_sort Busaleh, Mariam
collection PubMed
description Masses are one of the early signs of breast cancer, and the survival rate of women suffering from breast cancer can be improved if masses can be correctly identified as benign or malignant. However, their classification is challenging due to the similarity in texture patterns of both types of mass. The existing methods for this problem have low sensitivity and specificity. Based on the hypothesis that diverse contextual information of a mass region forms a strong indicator for discriminating benign and malignant masses and the idea of the ensemble classifier, we introduce a computer-aided system for this problem. The system uses multiple regions of interest (ROIs) encompassing a mass region for modeling diverse contextual information, a single ResNet-50 model (or its density-specific modification) as a backbone for local decisions, and stacking with SVM as a base model to predict the final decision. A data augmentation technique is introduced for fine-tuning the backbone model. The system was thoroughly evaluated on the benchmark CBIS-DDSM dataset using its provided data split protocol, and it achieved a sensitivity of 98.48% and a specificity of 92.31%. Furthermore, it was found that the system gives higher performance if it is trained and tested using the data from a specific breast density BI-RADS class. The system does not need to fine-tune/train multiple CNN models; it introduces diverse contextual information by multiple ROIs. The comparison shows that the method outperforms the state-of-the-art methods for classifying mass regions into benign and malignant. It will help radiologists reduce their burden and enhance their sensitivity in the prediction of malignant masses.
format Online
Article
Text
id pubmed-8615673
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-86156732021-11-26 Breast Mass Classification Using Diverse Contextual Information and Convolutional Neural Network Busaleh, Mariam Hussain, Muhammad Aboalsamh, Hatim A. Amin, Fazal-e- Biosensors (Basel) Article Masses are one of the early signs of breast cancer, and the survival rate of women suffering from breast cancer can be improved if masses can be correctly identified as benign or malignant. However, their classification is challenging due to the similarity in texture patterns of both types of mass. The existing methods for this problem have low sensitivity and specificity. Based on the hypothesis that diverse contextual information of a mass region forms a strong indicator for discriminating benign and malignant masses and the idea of the ensemble classifier, we introduce a computer-aided system for this problem. The system uses multiple regions of interest (ROIs) encompassing a mass region for modeling diverse contextual information, a single ResNet-50 model (or its density-specific modification) as a backbone for local decisions, and stacking with SVM as a base model to predict the final decision. A data augmentation technique is introduced for fine-tuning the backbone model. The system was thoroughly evaluated on the benchmark CBIS-DDSM dataset using its provided data split protocol, and it achieved a sensitivity of 98.48% and a specificity of 92.31%. Furthermore, it was found that the system gives higher performance if it is trained and tested using the data from a specific breast density BI-RADS class. The system does not need to fine-tune/train multiple CNN models; it introduces diverse contextual information by multiple ROIs. The comparison shows that the method outperforms the state-of-the-art methods for classifying mass regions into benign and malignant. It will help radiologists reduce their burden and enhance their sensitivity in the prediction of malignant masses. MDPI 2021-10-26 /pmc/articles/PMC8615673/ /pubmed/34821634 http://dx.doi.org/10.3390/bios11110419 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Busaleh, Mariam
Hussain, Muhammad
Aboalsamh, Hatim A.
Amin, Fazal-e-
Breast Mass Classification Using Diverse Contextual Information and Convolutional Neural Network
title Breast Mass Classification Using Diverse Contextual Information and Convolutional Neural Network
title_full Breast Mass Classification Using Diverse Contextual Information and Convolutional Neural Network
title_fullStr Breast Mass Classification Using Diverse Contextual Information and Convolutional Neural Network
title_full_unstemmed Breast Mass Classification Using Diverse Contextual Information and Convolutional Neural Network
title_short Breast Mass Classification Using Diverse Contextual Information and Convolutional Neural Network
title_sort breast mass classification using diverse contextual information and convolutional neural network
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8615673/
https://www.ncbi.nlm.nih.gov/pubmed/34821634
http://dx.doi.org/10.3390/bios11110419
work_keys_str_mv AT busalehmariam breastmassclassificationusingdiversecontextualinformationandconvolutionalneuralnetwork
AT hussainmuhammad breastmassclassificationusingdiversecontextualinformationandconvolutionalneuralnetwork
AT aboalsamhhatima breastmassclassificationusingdiversecontextualinformationandconvolutionalneuralnetwork
AT aminfazale breastmassclassificationusingdiversecontextualinformationandconvolutionalneuralnetwork